Hugging Face's logo

second-state
/
Palmyra-Fin-70B-32K-GGUF

Text Generation
GGUF
English
llama
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
287c4c7
·
verified ·
1 Parent(s): c78a1c8

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +95 -1
README.md CHANGED
@@ -1,3 +1,97 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ license_name: writer-open-model-license
4
+ license_link: https://writer.com/legal/open-model-license/
5
+ pipeline_tag: text-generation
6
+ base_model: Writer/Palmyra-Fin-70B-32K
7
+ model_creator: InternLM
8
+ model_name: Palmyra-Fin-70B-32K
9
+ quantized_by: Second State Inc.
10
+ language:
11
+ - en
12
  ---
13
+
14
+ <!-- header start -->
15
+ <!-- 200823 -->
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
20
+ <!-- header end -->
21
+
22
+ # Palmyra-Fin-70B-32K-GGUF
23
+
24
+ ## Original Model
25
+
26
+ [Writer/Palmyra-Fin-70B-32K](https://huggingface.co/Writer/Palmyra-Fin-70B-32K)
27
+
28
+ ## Run with LlamaEdge
29
+
30
+ - LlamaEdge version: [v0.13.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.13.1) and above
31
+
32
+ - Prompt template
33
+
34
+ - Prompt type: `llama-3-chat`
35
+
36
+ - Prompt string
37
+
38
+ ```text
39
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
40
+
41
+ {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
42
+
43
+ {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
44
+
45
+ {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
46
+
47
+ {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
48
+ ```
49
+
50
+ - Context size: `32000`
51
+
52
+ - Run as LlamaEdge service
53
+
54
+ ```bash
55
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Palmyra-Fin-70B-32K-Q5_K_M.gguf \
56
+ llama-api-server.wasm \
57
+ --prompt-template llama-3-chat \
58
+ --ctx-size 32000 \
59
+ --model-name Palmyra-Fin-70B-32K
60
+ ```
61
+
62
+ - Run as LlamaEdge command app
63
+
64
+ ```bash
65
+ wasmedge --dir .:. \
66
+ --nn-preload default:GGML:AUTO:Palmyra-Fin-70B-32K-Q5_K_M.gguf \
67
+ llama-chat.wasm \
68
+ --prompt-template llama-3-chat \
69
+ --ctx-size 32000
70
+ ```
71
+
72
+ ## Quantized GGUF Models
73
+
74
+ | Name | Quant method | Bits | Size | Use case |
75
+ | ---- | ---- | ---- | ---- | ----- |
76
+ | [Palmyra-Fin-70B-32K-Q2_K.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
77
+ | [Palmyra-Fin-70B-32K-Q3_K_L.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
78
+ | [Palmyra-Fin-70B-32K-Q3_K_M.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
79
+ | [Palmyra-Fin-70B-32K-Q3_K_S.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
80
+ | [Palmyra-Fin-70B-32K-Q4_0.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q4_0.gguf) | Q4_0 | 4 | 40.0 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
81
+ | [Palmyra-Fin-70B-32K-Q4_K_M.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
82
+ | [Palmyra-Fin-70B-32K-Q4_K_S.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q4_K_S.gguf) | Q4_K_S | 4 | 40.3 GB| small, greater quality loss |
83
+ | [Palmyra-Fin-70B-32K-Q5_0.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
84
+ | [Palmyra-Fin-70B-32K-Q5_K_M.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q5_K_M.gguf) | Q5_K_M | 5 | 49.9 GB| large, very low quality loss - recommended |
85
+ | [Palmyra-Fin-70B-32K-Q5_K_S.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
86
+ | [Palmyra-Fin-70B-32K-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 29.8 GB| very large, extremely low quality loss |
87
+ | [Palmyra-Fin-70B-32K-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 28.0 GB| very large, extremely low quality loss |
88
+ | [Palmyra-Fin-70B-32K-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
89
+ | [Palmyra-Fin-70B-32K-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
90
+ | [Palmyra-Fin-70B-32K-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 15.4 GB| very large, extremely low quality loss - not recommended |
91
+ | [Palmyra-Fin-70B-32K-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-f16-00001-of-00005.gguf) | f16 | 16 | 30.0 GB| |
92
+ | [Palmyra-Fin-70B-32K-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-f16-00002-of-00005.gguf) | f16 | 16 | 29.6 GB| |
93
+ | [Palmyra-Fin-70B-32K-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-f16-00003-of-00005.gguf) | f16 | 16 | 29.9 GB| |
94
+ | [Palmyra-Fin-70B-32K-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-f16-00004-of-00005.gguf) | f16 | 16 | 29.6 GB| |
95
+ | [Palmyra-Fin-70B-32K-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Palmyra-Fin-70B-32K-GGUF/blob/main/Palmyra-Fin-70B-32K-f16-00005-of-00005.gguf) | f16 | 16 | 22.2 GB| |
96
+
97
+ *Quantized with llama.cpp b3499*